##// END OF EJS Templates
util: lower water mark when removing nodes after cost limit reached...
util: lower water mark when removing nodes after cost limit reached See the inline comment for the reasoning here. This is a pretty common strategy for garbage collectors, other cache-like primtives. The performance impact is substantial: $ hg perflrucachedict --size 4 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 100 ! inserts w/ cost limit ! wall 1.659181 comb 1.650000 user 1.650000 sys 0.000000 (best of 7) ! wall 1.722122 comb 1.720000 user 1.720000 sys 0.000000 (best of 6) ! mixed w/ cost limit ! wall 1.139955 comb 1.140000 user 1.140000 sys 0.000000 (best of 9) ! wall 1.182513 comb 1.180000 user 1.180000 sys 0.000000 (best of 9) $ hg perflrucachedict --size 1000 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 10000 ! inserts ! wall 0.679546 comb 0.680000 user 0.680000 sys 0.000000 (best of 15) ! sets ! wall 0.825147 comb 0.830000 user 0.830000 sys 0.000000 (best of 13) ! inserts w/ cost limit ! wall 25.105273 comb 25.080000 user 25.080000 sys 0.000000 (best of 3) ! wall 1.724397 comb 1.720000 user 1.720000 sys 0.000000 (best of 6) ! mixed ! wall 0.807096 comb 0.810000 user 0.810000 sys 0.000000 (best of 13) ! mixed w/ cost limit ! wall 12.104470 comb 12.070000 user 12.070000 sys 0.000000 (best of 3) ! wall 1.190563 comb 1.190000 user 1.190000 sys 0.000000 (best of 9) $ hg perflrucachedict --size 1000 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 10000 --mixedgetfreq 90 ! inserts ! wall 0.711177 comb 0.710000 user 0.710000 sys 0.000000 (best of 14) ! sets ! wall 0.846992 comb 0.850000 user 0.850000 sys 0.000000 (best of 12) ! inserts w/ cost limit ! wall 25.963028 comb 25.960000 user 25.960000 sys 0.000000 (best of 3) ! wall 2.184311 comb 2.180000 user 2.180000 sys 0.000000 (best of 5) ! mixed ! wall 0.728256 comb 0.730000 user 0.730000 sys 0.000000 (best of 14) ! mixed w/ cost limit ! wall 3.174256 comb 3.170000 user 3.170000 sys 0.000000 (best of 4) ! wall 0.773186 comb 0.770000 user 0.770000 sys 0.000000 (best of 13) $ hg perflrucachedict --size 100000 --gets 1000000 --sets 1000000 --mixed 1000000 --mixedgetfreq 90 --costlimit 5000000 ! gets ! wall 1.191368 comb 1.190000 user 1.190000 sys 0.000000 (best of 9) ! wall 1.195304 comb 1.190000 user 1.190000 sys 0.000000 (best of 9) ! inserts ! wall 0.950995 comb 0.950000 user 0.950000 sys 0.000000 (best of 11) ! inserts w/ cost limit ! wall 1.589732 comb 1.590000 user 1.590000 sys 0.000000 (best of 7) ! sets ! wall 1.094941 comb 1.100000 user 1.090000 sys 0.010000 (best of 9) ! mixed ! wall 0.936420 comb 0.940000 user 0.930000 sys 0.010000 (best of 10) ! mixed w/ cost limit ! wall 0.882780 comb 0.870000 user 0.870000 sys 0.000000 (best of 11) This puts us ~2x slower than caches without cost accounting. And for read-heavy workloads (the prime use cases for caches), performance is nearly identical. In the worst case (pure write workloads with cost accounting enabled), we're looking at ~1.5us per insert on large caches. That seems "fast enough." Differential Revision: https://phab.mercurial-scm.org/D4505

File last commit:

r39280:73cf21b2 default
r39606:f296c0b3 default
Show More
repair.py
437 lines | 15.2 KiB | text/x-python | PythonLexer
# repair.py - functions for repository repair for mercurial
#
# Copyright 2005, 2006 Chris Mason <mason@suse.com>
# Copyright 2007 Matt Mackall
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from __future__ import absolute_import
import errno
import hashlib
from .i18n import _
from .node import (
hex,
short,
)
from . import (
bundle2,
changegroup,
discovery,
error,
exchange,
obsolete,
obsutil,
pycompat,
util,
)
from .utils import (
stringutil,
)
def backupbundle(repo, bases, heads, node, suffix, compress=True,
obsolescence=True):
"""create a bundle with the specified revisions as a backup"""
backupdir = "strip-backup"
vfs = repo.vfs
if not vfs.isdir(backupdir):
vfs.mkdir(backupdir)
# Include a hash of all the nodes in the filename for uniqueness
allcommits = repo.set('%ln::%ln', bases, heads)
allhashes = sorted(c.hex() for c in allcommits)
totalhash = hashlib.sha1(''.join(allhashes)).digest()
name = "%s/%s-%s-%s.hg" % (backupdir, short(node),
hex(totalhash[:4]), suffix)
cgversion = changegroup.localversion(repo)
comp = None
if cgversion != '01':
bundletype = "HG20"
if compress:
comp = 'BZ'
elif compress:
bundletype = "HG10BZ"
else:
bundletype = "HG10UN"
outgoing = discovery.outgoing(repo, missingroots=bases, missingheads=heads)
contentopts = {
'cg.version': cgversion,
'obsolescence': obsolescence,
'phases': True,
}
return bundle2.writenewbundle(repo.ui, repo, 'strip', name, bundletype,
outgoing, contentopts, vfs, compression=comp)
def _collectfiles(repo, striprev):
"""find out the filelogs affected by the strip"""
files = set()
for x in pycompat.xrange(striprev, len(repo)):
files.update(repo[x].files())
return sorted(files)
def _collectrevlog(revlog, striprev):
_, brokenset = revlog.getstrippoint(striprev)
return [revlog.linkrev(r) for r in brokenset]
def _collectmanifest(repo, striprev):
return _collectrevlog(repo.manifestlog.getstorage(b''), striprev)
def _collectbrokencsets(repo, files, striprev):
"""return the changesets which will be broken by the truncation"""
s = set()
s.update(_collectmanifest(repo, striprev))
for fname in files:
s.update(_collectrevlog(repo.file(fname), striprev))
return s
def strip(ui, repo, nodelist, backup=True, topic='backup'):
# This function requires the caller to lock the repo, but it operates
# within a transaction of its own, and thus requires there to be no current
# transaction when it is called.
if repo.currenttransaction() is not None:
raise error.ProgrammingError('cannot strip from inside a transaction')
# Simple way to maintain backwards compatibility for this
# argument.
if backup in ['none', 'strip']:
backup = False
repo = repo.unfiltered()
repo.destroying()
cl = repo.changelog
# TODO handle undo of merge sets
if isinstance(nodelist, str):
nodelist = [nodelist]
striplist = [cl.rev(node) for node in nodelist]
striprev = min(striplist)
files = _collectfiles(repo, striprev)
saverevs = _collectbrokencsets(repo, files, striprev)
# Some revisions with rev > striprev may not be descendants of striprev.
# We have to find these revisions and put them in a bundle, so that
# we can restore them after the truncations.
# To create the bundle we use repo.changegroupsubset which requires
# the list of heads and bases of the set of interesting revisions.
# (head = revision in the set that has no descendant in the set;
# base = revision in the set that has no ancestor in the set)
tostrip = set(striplist)
saveheads = set(saverevs)
for r in cl.revs(start=striprev + 1):
if any(p in tostrip for p in cl.parentrevs(r)):
tostrip.add(r)
if r not in tostrip:
saverevs.add(r)
saveheads.difference_update(cl.parentrevs(r))
saveheads.add(r)
saveheads = [cl.node(r) for r in saveheads]
# compute base nodes
if saverevs:
descendants = set(cl.descendants(saverevs))
saverevs.difference_update(descendants)
savebases = [cl.node(r) for r in saverevs]
stripbases = [cl.node(r) for r in tostrip]
stripobsidx = obsmarkers = ()
if repo.ui.configbool('devel', 'strip-obsmarkers'):
obsmarkers = obsutil.exclusivemarkers(repo, stripbases)
if obsmarkers:
stripobsidx = [i for i, m in enumerate(repo.obsstore)
if m in obsmarkers]
# For a set s, max(parents(s) - s) is the same as max(heads(::s - s)), but
# is much faster
newbmtarget = repo.revs('max(parents(%ld) - (%ld))', tostrip, tostrip)
if newbmtarget:
newbmtarget = repo[newbmtarget.first()].node()
else:
newbmtarget = '.'
bm = repo._bookmarks
updatebm = []
for m in bm:
rev = repo[bm[m]].rev()
if rev in tostrip:
updatebm.append(m)
# create a changegroup for all the branches we need to keep
backupfile = None
vfs = repo.vfs
node = nodelist[-1]
if backup:
backupfile = backupbundle(repo, stripbases, cl.heads(), node, topic)
repo.ui.status(_("saved backup bundle to %s\n") %
vfs.join(backupfile))
repo.ui.log("backupbundle", "saved backup bundle to %s\n",
vfs.join(backupfile))
tmpbundlefile = None
if saveheads:
# do not compress temporary bundle if we remove it from disk later
#
# We do not include obsolescence, it might re-introduce prune markers
# we are trying to strip. This is harmless since the stripped markers
# are already backed up and we did not touched the markers for the
# saved changesets.
tmpbundlefile = backupbundle(repo, savebases, saveheads, node, 'temp',
compress=False, obsolescence=False)
with ui.uninterruptable():
try:
with repo.transaction("strip") as tr:
offset = len(tr.entries)
tr.startgroup()
cl.strip(striprev, tr)
stripmanifest(repo, striprev, tr, files)
for fn in files:
repo.file(fn).strip(striprev, tr)
tr.endgroup()
for i in pycompat.xrange(offset, len(tr.entries)):
file, troffset, ignore = tr.entries[i]
with repo.svfs(file, 'a', checkambig=True) as fp:
fp.truncate(troffset)
if troffset == 0:
repo.store.markremoved(file)
deleteobsmarkers(repo.obsstore, stripobsidx)
del repo.obsstore
repo.invalidatevolatilesets()
repo._phasecache.filterunknown(repo)
if tmpbundlefile:
ui.note(_("adding branch\n"))
f = vfs.open(tmpbundlefile, "rb")
gen = exchange.readbundle(ui, f, tmpbundlefile, vfs)
if not repo.ui.verbose:
# silence internal shuffling chatter
repo.ui.pushbuffer()
tmpbundleurl = 'bundle:' + vfs.join(tmpbundlefile)
txnname = 'strip'
if not isinstance(gen, bundle2.unbundle20):
txnname = "strip\n%s" % util.hidepassword(tmpbundleurl)
with repo.transaction(txnname) as tr:
bundle2.applybundle(repo, gen, tr, source='strip',
url=tmpbundleurl)
if not repo.ui.verbose:
repo.ui.popbuffer()
f.close()
with repo.transaction('repair') as tr:
bmchanges = [(m, repo[newbmtarget].node()) for m in updatebm]
bm.applychanges(repo, tr, bmchanges)
# remove undo files
for undovfs, undofile in repo.undofiles():
try:
undovfs.unlink(undofile)
except OSError as e:
if e.errno != errno.ENOENT:
ui.warn(_('error removing %s: %s\n') %
(undovfs.join(undofile),
stringutil.forcebytestr(e)))
except: # re-raises
if backupfile:
ui.warn(_("strip failed, backup bundle stored in '%s'\n")
% vfs.join(backupfile))
if tmpbundlefile:
ui.warn(_("strip failed, unrecovered changes stored in '%s'\n")
% vfs.join(tmpbundlefile))
ui.warn(_("(fix the problem, then recover the changesets with "
"\"hg unbundle '%s'\")\n") % vfs.join(tmpbundlefile))
raise
else:
if tmpbundlefile:
# Remove temporary bundle only if there were no exceptions
vfs.unlink(tmpbundlefile)
repo.destroyed()
# return the backup file path (or None if 'backup' was False) so
# extensions can use it
return backupfile
def safestriproots(ui, repo, nodes):
"""return list of roots of nodes where descendants are covered by nodes"""
torev = repo.unfiltered().changelog.rev
revs = set(torev(n) for n in nodes)
# tostrip = wanted - unsafe = wanted - ancestors(orphaned)
# orphaned = affected - wanted
# affected = descendants(roots(wanted))
# wanted = revs
tostrip = set(repo.revs('%ld-(::((roots(%ld)::)-%ld))', revs, revs, revs))
notstrip = revs - tostrip
if notstrip:
nodestr = ', '.join(sorted(short(repo[n].node()) for n in notstrip))
ui.warn(_('warning: orphaned descendants detected, '
'not stripping %s\n') % nodestr)
return [c.node() for c in repo.set('roots(%ld)', tostrip)]
class stripcallback(object):
"""used as a transaction postclose callback"""
def __init__(self, ui, repo, backup, topic):
self.ui = ui
self.repo = repo
self.backup = backup
self.topic = topic or 'backup'
self.nodelist = []
def addnodes(self, nodes):
self.nodelist.extend(nodes)
def __call__(self, tr):
roots = safestriproots(self.ui, self.repo, self.nodelist)
if roots:
strip(self.ui, self.repo, roots, self.backup, self.topic)
def delayedstrip(ui, repo, nodelist, topic=None, backup=True):
"""like strip, but works inside transaction and won't strip irreverent revs
nodelist must explicitly contain all descendants. Otherwise a warning will
be printed that some nodes are not stripped.
Will do a backup if `backup` is True. The last non-None "topic" will be
used as the backup topic name. The default backup topic name is "backup".
"""
tr = repo.currenttransaction()
if not tr:
nodes = safestriproots(ui, repo, nodelist)
return strip(ui, repo, nodes, backup=backup, topic=topic)
# transaction postclose callbacks are called in alphabet order.
# use '\xff' as prefix so we are likely to be called last.
callback = tr.getpostclose('\xffstrip')
if callback is None:
callback = stripcallback(ui, repo, backup=backup, topic=topic)
tr.addpostclose('\xffstrip', callback)
if topic:
callback.topic = topic
callback.addnodes(nodelist)
def stripmanifest(repo, striprev, tr, files):
revlog = repo.manifestlog.getstorage(b'')
revlog.strip(striprev, tr)
striptrees(repo, tr, striprev, files)
def striptrees(repo, tr, striprev, files):
if 'treemanifest' in repo.requirements: # safe but unnecessary
# otherwise
for unencoded, encoded, size in repo.store.datafiles():
if (unencoded.startswith('meta/') and
unencoded.endswith('00manifest.i')):
dir = unencoded[5:-12]
repo.manifestlog.getstorage(dir).strip(striprev, tr)
def rebuildfncache(ui, repo):
"""Rebuilds the fncache file from repo history.
Missing entries will be added. Extra entries will be removed.
"""
repo = repo.unfiltered()
if 'fncache' not in repo.requirements:
ui.warn(_('(not rebuilding fncache because repository does not '
'support fncache)\n'))
return
with repo.lock():
fnc = repo.store.fncache
# Trigger load of fncache.
if 'irrelevant' in fnc:
pass
oldentries = set(fnc.entries)
newentries = set()
seenfiles = set()
progress = ui.makeprogress(_('rebuilding'), unit=_('changesets'),
total=len(repo))
for rev in repo:
progress.update(rev)
ctx = repo[rev]
for f in ctx.files():
# This is to minimize I/O.
if f in seenfiles:
continue
seenfiles.add(f)
i = 'data/%s.i' % f
d = 'data/%s.d' % f
if repo.store._exists(i):
newentries.add(i)
if repo.store._exists(d):
newentries.add(d)
progress.complete()
if 'treemanifest' in repo.requirements: # safe but unnecessary otherwise
for dir in util.dirs(seenfiles):
i = 'meta/%s/00manifest.i' % dir
d = 'meta/%s/00manifest.d' % dir
if repo.store._exists(i):
newentries.add(i)
if repo.store._exists(d):
newentries.add(d)
addcount = len(newentries - oldentries)
removecount = len(oldentries - newentries)
for p in sorted(oldentries - newentries):
ui.write(_('removing %s\n') % p)
for p in sorted(newentries - oldentries):
ui.write(_('adding %s\n') % p)
if addcount or removecount:
ui.write(_('%d items added, %d removed from fncache\n') %
(addcount, removecount))
fnc.entries = newentries
fnc._dirty = True
with repo.transaction('fncache') as tr:
fnc.write(tr)
else:
ui.write(_('fncache already up to date\n'))
def deleteobsmarkers(obsstore, indices):
"""Delete some obsmarkers from obsstore and return how many were deleted
'indices' is a list of ints which are the indices
of the markers to be deleted.
Every invocation of this function completely rewrites the obsstore file,
skipping the markers we want to be removed. The new temporary file is
created, remaining markers are written there and on .close() this file
gets atomically renamed to obsstore, thus guaranteeing consistency."""
if not indices:
# we don't want to rewrite the obsstore with the same content
return
left = []
current = obsstore._all
n = 0
for i, m in enumerate(current):
if i in indices:
n += 1
continue
left.append(m)
newobsstorefile = obsstore.svfs('obsstore', 'w', atomictemp=True)
for bytes in obsolete.encodemarkers(left, True, obsstore._version):
newobsstorefile.write(bytes)
newobsstorefile.close()
return n